1# Agent Settings
2
3Learn about all the settings you can customize in Zed's Agent Panel.
4
5## Model Settings {#model-settings}
6
7### Default Model {#default-model}
8
9If you're using [Zed's hosted LLM service](./plans-and-usage.md), it sets `claude-sonnet-4` as the default model.
10But if you're not subscribed to it or simply just want to change it, you can do it so either via the model dropdown in the Agent Panel's bottom-right corner or by manually editing the `default_model` object in your settings:
11
12```json
13{
14 "agent": {
15 "default_model": {
16 "provider": "zed.dev",
17 "model": "gpt-4o"
18 }
19 }
20}
21```
22
23### Feature-specific Models {#feature-specific-models}
24
25Assign distinct and specific models for the following AI-powered features in Zed:
26
27- Thread summary model: Used for generating thread summaries
28- Inline assistant model: Used for the inline assistant feature
29- Commit message model: Used for generating Git commit messages
30
31```json
32{
33 "agent": {
34 "default_model": {
35 "provider": "zed.dev",
36 "model": "claude-sonnet-4"
37 },
38 "inline_assistant_model": {
39 "provider": "anthropic",
40 "model": "claude-3-5-sonnet"
41 },
42 "commit_message_model": {
43 "provider": "openai",
44 "model": "gpt-4o-mini"
45 },
46 "thread_summary_model": {
47 "provider": "google",
48 "model": "gemini-2.0-flash"
49 }
50 }
51}
52```
53
54> If a custom model isn't set for one of these features, they automatically fall back to using the default model.
55
56### Alternative Models for Inline Assists {#alternative-assists}
57
58The Inline Assist feature in particular has the capacity to perform multiple generations in parallel using different models.
59That is possible by assigning more than one model to it, taking the configuration shown above one step further.
60
61When configured, the inline assist UI will surface controls to cycle between the outputs generated by each model.
62
63The models you specify here are always used in _addition_ to your [default model](#default-model).
64
65For example, the following configuration will generate two outputs for every assist.
66One with Claude Sonnet 4 (the default model), and one with GPT-4o.
67
68```json
69{
70 "agent": {
71 "default_model": {
72 "provider": "zed.dev",
73 "model": "claude-sonnet-4"
74 },
75 "inline_alternatives": [
76 {
77 "provider": "zed.dev",
78 "model": "gpt-4o"
79 }
80 ]
81 }
82}
83```
84
85### Model Temperature
86
87Specify a custom temperature for a provider and/or model:
88
89```json
90"model_parameters": [
91 // To set parameters for all requests to OpenAI models:
92 {
93 "provider": "openai",
94 "temperature": 0.5
95 },
96 // To set parameters for all requests in general:
97 {
98 "temperature": 0
99 },
100 // To set parameters for a specific provider and model:
101 {
102 "provider": "zed.dev",
103 "model": "claude-sonnet-4",
104 "temperature": 1.0
105 }
106],
107```
108
109## Agent Panel Settings {#agent-panel-settings}
110
111Note that some of these settings are also surfaced in the Agent Panel's settings UI, which you can access either via the `agent: open settings` action or by the dropdown menu on the top-right corner of the panel.
112
113### Default View
114
115Use the `default_view` setting to change the default view of the Agent Panel.
116You can choose between `thread` (the default) and `text_thread`:
117
118```json
119{
120 "agent": {
121 "default_view": "text_thread"
122 }
123}
124```
125
126### Font Size
127
128Use the `agent_font_size` setting to change the font size of rendered agent responses in the panel.
129
130```json
131{
132 "agent": {
133 "agent_font_size": 18
134 }
135}
136```
137
138> (Preview Version Note): Editors in the Agent Panel—whether that is the main message textarea or previous messages—use monospace fonts and therefore, are controlled by the `buffer_font_size` setting, which is defined globally in your `settings.json`.
139
140### Auto-run Commands
141
142Control whether you want to allow the agent to run commands without asking you for permission.
143The default value is `false`.
144
145```json
146{
147 "agent": {
148 "always_allow_tool_actions": true
149 }
150}
151```
152
153> This setting is available via the Agent Panel's settings UI.
154
155### Single-file Review
156
157Control whether you want to see review actions (accept & reject) in single buffers after the agent is done performing edits.
158The default value is `false`.
159
160```json
161{
162 "agent": {
163 "single_file_review": true
164 }
165}
166```
167
168When set to false, these controls are only available in the multibuffer review tab.
169
170> This setting is available via the Agent Panel's settings UI.
171
172### Sound Notification
173
174Control whether you want to hear a notification sound when the agent is done generating changes or needs your input.
175The default value is `false`.
176
177```json
178{
179 "agent": {
180 "play_sound_when_agent_done": true
181 }
182}
183```
184
185> This setting is available via the Agent Panel's settings UI.
186
187### Message Editor Size
188
189Use the `message_editor_min_lines` setting to control minimum number of lines of height the agent message editor should have.
190It is set to `4` by default, and the max number of lines is always double of the minimum.
191
192```json
193{
194 "agent": {
195 "message_editor_min_lines": 4
196 }
197}
198```
199
200> This setting is currently available only in Preview.
201
202### Modifier to Send
203
204Make a modifier (`cmd` on macOS, `ctrl` on Linux) required to send messages.
205This is encouraged for more thoughtful prompt crafting.
206The default value is `false`.
207
208```json
209{
210 "agent": {
211 "use_modifier_to_send": true
212 }
213}
214```
215
216> This setting is available via the Agent Panel's settings UI.
217
218### Edit Card
219
220Use the `expand_edit_card` setting to control whether edit cards show the full diff in the Agent Panel.
221It is set to `true` by default, but if set to false, the card's height is capped to a certain number of lines, requiring a click to be expanded.
222
223```json
224{
225 "agent": {
226 "expand_edit_card": false
227 }
228}
229```
230
231### Terminal Card
232
233Use the `expand_terminal_card` setting to control whether terminal cards show the command output in the Agent Panel.
234It is set to `true` by default, but if set to false, the card will be fully collapsed even while the command is running, requiring a click to be expanded.
235
236```json
237{
238 "agent": {
239 "expand_terminal_card": false
240 }
241}
242```
243
244### Feedback Controls
245
246Control whether you want to see the thumbs up/down buttons to give Zed feedback about the agent's performance.
247The default value is `true`.
248
249```json
250{
251 "agent": {
252 "enable_feedback": false
253 }
254}
255```